A Novel Approach to Fuzzy-Based Facial Feature Extraction and Face Recognition

Aniruddha Dey, Manas Ghosh

Abstract


Generalized two-dimensional Fisher’s linear discriminant (G-2DFLD) is an effective feature extraction technique that maximizes class separability along row and column directions simultaneously. In this paper, we propose a fuzzy logic-based feature extraction technique, called fuzzy generalized two-dimensional Fisher’s linear discriminant analysis (FG-2DLDA) method which is extended version of the G-2DFLD method. This paper also explores the use of the proposed method for face recognition using radial basis function (RBF) neural network as a classifier. Fuzzy membership matrix values are calculated by fuzzy k-nearest neighbour (Fk-NN) algorithm for the training samples. These fuzzy membership values are combined with the training samples to generate global mean and class-wise mean training images. Thereafter, the global and class-wise mean images are used to generate fuzzy within- and between-class scatter matrices along the both directions. Finally, by solving the Eigen value problems of these scatter matrices, we find the optimal fuzzy projection vectors, which actually used to generate more discriminant features. Our proposed method has been evaluated on the four public face databases using RBF neural network and establish that the proposed FG-2DLDA method provides favourable recognition rates than some contemporary face recognition methods.

Full Text:

PDF

References


R. Chellappa, C. L. Wilson, and S. Sirohey. Human and machine recognition of faces: a survey. Proc. IEEE vol. 83, 705–740, 1995.

W. Zhao, R. Chellappa, and P. J. Phillops. A. Rosenfeld. Face recognition: a literature survey. ACM Comput. Surveys. 35: 399–458, 2003.

A. S. Tolba, A.H. El-Baz, and A.A. El-Harby. Face recognition: a literature review. Int. J. Signal Process, 2: 88–103, 2006.

H. Zhou, A. Mian, L. Wei, D. Creighton, M. Hossny, and S. Nahavandi. Recent advances on singlemodal and multimodal face recognition: a survey. IEEE Trans. Human Machine Systems, 44(6): 701–716, 2014.

P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman. Eigenfaces versus fisherfaces: recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell., 19:711–720, 1997.

B. Poon, M. A. Amin, and H. Yan. Performance evaluation and comparison of PCA Based human face recognition methods for distorted images. International Journal of Machine Learning and Cybernetics, 2(4): 245–259, 2011.

G. J. Alvarado, W. Pedrycz,•M. Reformat, and K.-C. Kwak. Deterioration of visual information in face classification using eigenfaces and fisherfaces. Machine Vision and Applications, 17(1): 68–82, 2006.

L. F Chen, H. Y Mark Liao, M. T. Ko, J.C Lin, and G. J.Yu. A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recogn., 33: 1713–26, 2000.

H. Yu, and J. Yang. A direct LDA algorithm for high-dimensional data-with application to face recognition. Pattern Recogn. 34: 2067–70, 2001.

X. S. Zhuang, and D. Q. Dai. Improved discriminant analysis for high-dimensional data and its application to face recognition. Pattern Recogn., 40(5): 1570-1578, 2007.

D. Swets, and J. Weng. Using discriminant eigenfeatures for image retrieval. IEEE Trans. Pattern Anal. Machine Intell., 18(8) 831–836, 1996.

J. Friedman. Regularized discriminant analysis. J. Am. Stat. Assoc., 165– 175, 1989.

R. Huang, Q. Liu, H. Lu, and S. Ma. Solving the small sample size problem of lda. In Proceedings of the 16th International Conference on Pattern Recognition,3, pages 29–32, 2002.

L. Chen, H. Liao, M. Ko, J. Lin, and G. Yu. A new lda-based face recognition system which can solve the small sample size problem. Pattern Recogn., 33 (10): 1713–1726, 2000.

H. Yu, and J. Yang. A direct lda algorithm for high-dimensional data-with application to face recognition. Pattern Recogn., 34 (10): 2067- 2075, 2001.

M. S. Bartlet, J. R. Movellan, and T. J. Sejnowski. Face recognition by independent component analysis. IEEE Trans. Neural Netw., 13(6):1450-1464, 2002.

J. Yang, D. Zhang, A. F. Frangi, and J. Y. Yang. Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Trans. Pattern Anal. Mach. Intell., 26(1):131–137,2004.

H. Xiong, M. N. S. Swamy, and M. O. Ahmad. Two-dimensional FLD for face recognition. Pattern Recogn., 38(7):1121–1124, 2005.

S. Chowdhury, J. K. Sing, D. K. Basu, and M. Nasipuri. Face recognition by generalized two-dimensional FLD method and multi-class support vector machines. Appl. Soft Comput.,11(7):4282–4292, 2011.

J. M. Keller, M. R. Gray, and J. A. Givens. A fuzzy k-nearest neighbor algorithm. IEEE Trans. Syst. Man Cybernet., 15(4):580–585, 1985.

K. C. Kwak, and W. Pedrycz. Face recognition using a fuzzy fisherface classifier. Journal of the Pattern Recogn. 38(10):1717-1732, 2005.

W. Yang, J. Wang, M. Ren, and J. Yang. Fuzzy 2-dimensional FLD for face recognition. Journal of Information and Computing Science, 4(3): 233-239, 2009.

W. Yang, J. Wang, M. Ren, L. Zhang, and J. Yang. Feature extraction using fuzzy inverse FDA. Neurocomputing, 72(13- 15): 3384–3390, 2009.

X. N.Song, Y. J. Zheng, X. J.Wu, X. B.Yang, and J. Y.Yang. A complete fuzzy discriminant analysis approach for face recognition. Applied Soft Computing, 10: 208-214, 2010.

L. Xiaodong, F. Shumin, and T. Zhang. Weighted maximum scatter difference based feature extraction and its application to face recognition. Machine Vision and Applications, 22: 591-595, 2013.

M. Zhao, T. W. S. Chow, and Z. Zhang. Random walk-based fuzzy linear discriminant analysis for dimensionality reduction. Soft Computing, 16:1393-1409, 2012.

J. Wang, W. Yang, and J. Yang. Face recognition using fuzzy maximum scatter discriminant analysis. Neural Computing & Application, 23: 957-964, 2013.

X. Li, and A. Song. Fuzzy MSD based feature extraction method for extraction. Neurocomputing, 122: 266-271, 2013.

X. Li. Face recognition method based on fuzzy 2DPCA. Journal of Electrical and Computer Engineering, 2014:1- 7, 2014.

N. Zheng, L. Qi, and L. Guan. Generalised multiple maximum scatter difference feature extraction using QR decomposition. Journal of visual Communication Image Representation, 25:1460-1471, 2014.

J.K. Sing. A novel Gaussian probabilistic generalized 2DLDA for feature extraction and face recognition. In Proceedings of the IEEE Conference on Computer Graphics, Vision and Information Security, pages 258-263, 2015.

P. Huang, Z. Yang, and C. Chen. Fuzzy local discriminant embedding for image feature extraction. Computers and Electrical Engineering, 46:231-240, 2015.

J. Xu, Z. Gu, and K. Xie. Fuzzy local mean discriminant analysis for dimensionality reduction. Neural Processing Letter, 44:701-718, 2016.

P. Huang, G. Gao, C. Qian, G. Yang, and Z. Yang. Fuzzy linear regression discriminant projection for face recognition. IEEE Access, 23:169-174, 2017.

J. K. Sing, D. K. Basu, M. Nasipuri, and M. Kundu. Face recognition using point symmetry distance-based RBF network. Appl. Soft Comput., vol. 7, no. 1, pp. 58–70, January 2007.

J. K. Sing, S. Thakur, D. K. Basu, M. Nasipuri, and M. Kundu. High-speed face recognition using self-adaptive radial basis function neural networks. Neural Comput. Appl., 18(8), 979–990, 2009.

Q. Zhu, and Y. Xu. Multi-directional two dimensional PCA with matching score level fusion for face recognition. Neural Comput. & Applic., 23(1): 169-174, 2013.

The Yale face database .

P. J. Phillips, H. Moon, S. A. Rizvi, and P. J. Rauss. The FERET evaluation methodology for face-recognition algorithms. IEEE Trans. Pattern. Anal. Mach. Intell., 22: 1090–1104, 2000.

P. J. Phillips. The Facial Recognition Technology (FERET) database. , 2004.

The ORL face database, .

D. B. Graham, N. M. Allinson, H. Wechsler, P. J. Phillips, V. Bruce, F. Fogelman-Soulie, and T. S. Huang (Eds.), Characterizing virtual eigen signatures for general purpose face recognition: From theory to applications. NATO ASI Series F Computer and Systems Sciences, 163: 446–456, 1998.




DOI: https://doi.org/10.31449/inf.v43i4.2117

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.